[PATCH] D90174: [HIP] Fix regressions due to fp contract change

Wed Nov 4 09:45:12 PST 2020

yaxunl added a comment.

In D90174#2373829 <https://reviews.llvm.org/D90174#2373829>, @yaxunl wrote:

> In D90174#2371577 <https://reviews.llvm.org/D90174#2371577>, @rjmccall wrote:
>
>> Hmm.  Do we actually want this behavior of `fast` overriding pragmas?  What do other compilers do here?  It might be reasonable to just treat this as a bug.
>
> I think clang is just trying to follow gcc's behavior. However, this is undesirable in certain cases. Introducing 'faststd' gives us more choices to avoid the undesirable behavior.

For other compilers:

MSVC respects pragma with /fp:fast option:

https://godbolt.org/z/3rja55

Intel compiler also respects fp_contract pragma with -fp-model fast={1|2} option:

https://godbolt.org/z/fez86h

nvcc by default always fuse across statements and does not support pragmas to control fp contract

https://docs.nvidia.com/cuda/floating-point/index.html#controlling-fused-multiply-add

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90174/new/

https://reviews.llvm.org/D90174